Architecture-Aware Explanation Auditing for Industrial Visual Inspection 事件

Architecture-Aware Explanation Auditing for Industrial Visual Inspection arXiv:2605.14255v3 Announce Type: replace-cross Abstract: Industrial visual inspection systems increasingly rely on deep classifiers whose heatmap explanations may appear visually plausible while failing to identify the image regions that actually drive model decisions. This paper operationalizes an architecture-aware explanation audit protocol grounded in the native-readout hypothesis: the perturbation-based faithfulness